# Research Papers — 2025-10 · bundle page 6 of 217

> Full-text markdown of papers #251–300 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/6
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/5.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/7.md)

### MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts

Authors: Jingnan Gao, Zhe Wang, Xianze Fang, Xingyu Ren, Zhuo Chen, Shengqi Liu, Yuhao Cheng, Jiangjing Lyu, Xiaokang Yang, Yichao Yan
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27234v1

Recent advances in language and vision have demonstrated that scaling up model capacity consistently improves performance across diverse tasks. In 3D visual geometry reconstruction, large-scale training has likewise proven effective for learning versatile representations. However, further scaling of 3D models is challenging due to the complexity of geometric supervision and the diversity of 3D data. To overcome these limitations, we propose MoRE, a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture that dynamically routes features to task-specific experts, allowing them to specialize in complementary data aspects and enhance both scalability and adaptability. Aiming to improve robustness under real-world conditions, MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation. In addition, it integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction. MoRE is further optimized with tailored loss functions to ensure robust learning across diverse inputs and multiple geometric tasks. Extensive experiments demonstrate that MoRE achieves state-of-the-art performance across multiple benchmarks and supports effective downstream applications without extra computation.

---

### Mask-to-Height: A YOLOv11-Based Architecture for Joint Building Instance Segmentation and Height Classification from Satellite Imagery

Authors: Mahmoud El Hussieni, Bahadır K. Güntürk, Hasan F. Ateş, Oğuz Hanoğlu
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27224v1

Accurate building instance segmentation and height classification are critical for urban planning, 3D city modeling, and infrastructure monitoring. This paper presents a detailed analysis of YOLOv11, the recent advancement in the YOLO series of deep learning models, focusing on its application to joint building extraction and discrete height classification from satellite imagery. YOLOv11 builds on the strengths of earlier YOLO models by introducing a more efficient architecture that better combines features at different scales, improves object localization accuracy, and enhances performance in complex urban scenes. Using the DFC2023 Track 2 dataset -- which includes over 125,000 annotated buildings across 12 cities -- we evaluate YOLOv11's performance using metrics such as precision, recall, F1 score, and mean average precision (mAP). Our findings demonstrate that YOLOv11 achieves strong instance segmentation performance with 60.4\% mAP@50 and 38.3\% mAP@50--95 while maintaining robust classification accuracy across five predefined height tiers. The model excels in handling occlusions, complex building shapes, and class imbalance, particularly for rare high-rise structures. Comparative analysis confirms that YOLOv11 outperforms earlier multitask frameworks in both detection accuracy and inference speed, making it well-suited for real-time, large-scale urban mapping. This research highlights YOLOv11's potential to advance semantic urban reconstruction through streamlined categorical height modeling, offering actionable insights for future developments in remote sensing and geospatial intelligence.

---

### Soft Task-Aware Routing of Experts for Equivariant Representation Learning

Authors: Jaebyeong Jeon, Hyeonseo Jang, Jy-yong Sohn, Kibok Lee
Published: 2025-10-31
Categories: cs.LG, cs.AI, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2510.27222v1

Equivariant representation learning aims to capture variations induced by input transformations in the representation space, whereas invariant representation learning encodes semantic information by disregarding such transformations. Recent studies have shown that jointly learning both types of representations is often beneficial for downstream tasks, typically by employing separate projection heads. However, this design overlooks information shared between invariant and equivariant learning, which leads to redundant feature learning and inefficient use of model capacity. To address this, we introduce Soft Task-Aware Routing (STAR), a routing strategy for projection heads that models them as experts. STAR induces the experts to specialize in capturing either shared or task-specific information, thereby reducing redundant feature learning. We validate this effect by observing lower canonical correlations between invariant and equivariant embeddings. Experimental results show consistent improvements across diverse transfer learning tasks. The code is available at https://github.com/YonseiML/star.

---

### SpecAware: A Spectral-Content Aware Foundation Model for Unifying Multi-Sensor Learning in Hyperspectral Remote Sensing Mapping

Authors: Renjie Ji, Xue Wang, Chao Niu, Wen Zhang, Yong Mei, Kun Tan
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27219v2

Hyperspectral imaging (HSI) is a critical technique for fine-grained land-use and land-cover (LULC) mapping. However, the inherent heterogeneity of HSI data, particularly the variation in spectral channels across sensors, has long constrained the development of model generalization via transfer learning or joint training. Existing HSI foundation models show promise for different downstream tasks, but typically underutilize the critical guiding role of sensor meta-attributes and image semantic features, resulting in limited adaptability to cross-sensor joint learning. To address these issues, we propose SpecAware, which is a novel hyperspectral spectral-content aware foundation model for unifying multi-sensor learning for HSI mapping. To support this work, we constructed the Hyper-400K dataset, which is a new large-scale pre-training dataset with over 400\,k high-quality patches from diverse airborne AVIRIS sensors that cover two data processing levels (L1 and L2). The core of SpecAware is a hypernetwork-driven unified image embedding process for HSI data. Firstly, we designed a meta-content aware module to generate a unique conditional input for each HSI sample, tailored to each spectral band by fusing the sensor meta-attributes and its own image content. Secondly, we designed the HyperEmbedding module, where a sample-conditioned hypernetwork dynamically generates a pair of matrix factors for channel-wise encoding. This process implements two-step matrix factorization, consisting of adaptive spatial pattern extraction and latent semantic feature projection, yielding a unified hyperspectral token representation. Thus, SpecAware learns to capture and interpret spatial-spectral features across diverse scenes and sensors, enabling adaptive processing of variable spectral channels within a unified multi-sensor joint pre-training framework.

---

### Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness

Authors: Ren Tasai, Guang Li, Ren Togo, Takahiro Ogawa, Kenji Hirata, Minghui Tang, Takaaki Yoshimura, Hiroyuki Sugimori, Noriko Nishioka, Yukie Shimizu, Kohsuke Kudo, Miki Haseyama
Published: 2025-10-31
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.27213v1

We propose a novel continual self-supervised learning (CSSL) framework for simultaneously learning diverse features from multi-window-obtained chest computed tomography (CT) images and ensuring data privacy. Achieving a robust and highly generalizable model in medical image diagnosis is challenging, mainly because of issues, such as the scarcity of large-scale, accurately annotated datasets and domain shifts inherent to dynamic healthcare environments. Specifically, in chest CT, these domain shifts often arise from differences in window settings, which are optimized for distinct clinical purposes. Previous CSSL frameworks often mitigated domain shift by reusing past data, a typically impractical approach owing to privacy constraints. Our approach addresses these challenges by effectively capturing the relationship between previously learned knowledge and new information across different training stages through continual pretraining on unlabeled images. Specifically, by incorporating a latent replay-based mechanism into CSSL, our method mitigates catastrophic forgetting due to domain shifts during continual pretraining while ensuring data privacy. Additionally, we introduce a feature distillation technique that integrates Wasserstein distance-based knowledge distillation (WKD) and batch-knowledge ensemble (BKE), enhancing the ability of the model to learn meaningful, domain-shift-robust representations. Finally, we validate our approach using chest CT images obtained across two different window settings, demonstrating superior performance compared with other approaches.

---

### Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers

Authors: Henry Pritchard, Rahul Parhi
Published: 2025-10-31
Categories: math.OC, eess.SP, stat.ML
arXiv: https://arxiv.org/abs/2510.27211v7

It is known that the minimum-mean-squared-error (MMSE) denoiser under Gaussian noise can be written as a proximal operator, which suffices for asymptotic convergence of plug-and-play (PnP) methods but does not reveal the structure of the induced regularizer or give convergence rates. We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer is 1-weakly convex. Using this property, we derive (to the best of our knowledge) the first sublinear convergence guarantee for PnP proximal gradient descent with an MMSE denoiser. We validate the theory with a one-dimensional synthetic study that recovers the implicit regularizer. We also validate the theory with imaging experiments (deblurring and computed tomography), which exhibit the predicted sublinear behavior.

---

### GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation

Authors: Tao Liu, Chongyu Wang, Rongjie Li, Yingchen Yu, Xuming He, Bai Song
Published: 2025-10-31
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.27210v1

While Multimodal Large Language Models (MLLMs) have advanced GUI navigation agents, current approaches face limitations in cross-domain generalization and effective history utilization. We present a reasoning-enhanced framework that systematically integrates structured reasoning, action prediction, and history summarization. The structured reasoning component generates coherent Chain-of-Thought analyses combining progress estimation and decision reasoning, which inform both immediate action predictions and compact history summaries for future steps. Based on this framework, we train a GUI agent, \textbf{GUI-Rise}, through supervised fine-tuning on pseudo-labeled trajectories and reinforcement learning with Group Relative Policy Optimization (GRPO). This framework employs specialized rewards, including a history-aware objective, directly linking summary quality to subsequent action performance. Comprehensive evaluations on standard benchmarks demonstrate state-of-the-art results under identical training data conditions, with particularly strong performance in out-of-domain scenarios. These findings validate our framework's ability to maintain robust reasoning and generalization across diverse GUI navigation tasks. Code is available at https://leon022.github.io/GUI-Rise.

---

### Multi-Modal Feature Fusion for Spatial Morphology Analysis of Traditional Villages via Hierarchical Graph Neural Networks

Authors: Jiaxin Zhang, Zehong Zhu, Junye Deng, Yunqin Li, and Bowen Wang
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27208v1

Villages areas hold significant importance in the study of human-land relationships. However, with the advancement of urbanization, the gradual disappearance of spatial characteristics and the homogenization of landscapes have emerged as prominent issues. Existing studies primarily adopt a single-disciplinary perspective to analyze villages spatial morphology and its influencing factors, relying heavily on qualitative analysis methods. These efforts are often constrained by the lack of digital infrastructure and insufficient data. To address the current research limitations, this paper proposes a Hierarchical Graph Neural Network (HGNN) model that integrates multi-source data to conduct an in-depth analysis of villages spatial morphology. The framework includes two types of nodes-input nodes and communication nodes-and two types of edges-static input edges and dynamic communication edges. By combining Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT), the proposed model efficiently integrates multimodal features under a two-stage feature update mechanism. Additionally, based on existing principles for classifying villages spatial morphology, the paper introduces a relational pooling mechanism and implements a joint training strategy across 17 subtypes. Experimental results demonstrate that this method achieves significant performance improvements over existing approaches in multimodal fusion and classification tasks. Additionally, the proposed joint optimization of all sub-types lifts mean accuracy/F1 from 0.71/0.83 (independent models) to 0.82/0.90, driven by a 6% gain for parcel tasks. Our method provides scientific evidence for exploring villages spatial patterns and generative logic.

---

### Feature-Function Curvature Analysis: A Geometric Framework for Explaining Differentiable Models

Authors: Hamed Najafi, Dongsheng Luo, Jason Liu
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27207v1

Explainable AI (XAI) is critical for building trust in complex machine learning models, yet mainstream attribution methods often provide an incomplete, static picture of a model's final state. By collapsing a feature's role into a single score, they are confounded by non-linearity and interactions. To address this, we introduce Feature-Function Curvature Analysis (FFCA), a novel framework that analyzes the geometry of a model's learned function. FFCA produces a 4-dimensional signature for each feature, quantifying its: (1) Impact, (2) Volatility, (3) Non-linearity, and (4) Interaction. Crucially, we extend this framework into Dynamic Archetype Analysis, which tracks the evolution of these signatures throughout the training process. This temporal view moves beyond explaining what a model learned to revealing how it learns. We provide the first direct, empirical evidence of hierarchical learning, showing that models consistently learn simple linear effects before complex interactions. Furthermore, this dynamic analysis provides novel, practical diagnostics for identifying insufficient model capacity and predicting the onset of overfitting. Our comprehensive experiments demonstrate that FFCA, through its static and dynamic components, provides the essential geometric context that transforms model explanation from simple quantification to a nuanced, trustworthy analysis of the entire learning process.

---

### Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering

Authors: Kounianhua Du, Jianxing Liu, Kangning Zhang, Wenxiang Jiao, Yuan Lu, Jiarui Jin, Weiwen Liu, Yong Yu, Weinan Zhang
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27206v1

The rapid evolution of large language models (LLMs) has intensified the demand for effective personalization techniques that can adapt model behavior to individual user preferences. Despite the non-parametric methods utilizing the in-context learning ability of LLMs, recent parametric adaptation methods, including personalized parameter-efficient fine-tuning and reward modeling emerge. However, these methods face limitations in handling dynamic user patterns and high data sparsity scenarios, due to low adaptability and data efficiency. To address these challenges, we propose a fine-grained and instance-tailored steering framework that dynamically generates sample-level interference vectors from user data and injects them into the model's forward pass for personalized adaptation. Our approach introduces two key technical innovations: a fine-grained steering component that captures nuanced signals by hooking activations from attention and MLP layers, and an input-aware aggregation module that synthesizes these signals into contextually relevant enhancements. The method demonstrates high flexibility and data efficiency, excelling in fast-changing distribution and high data sparsity scenarios. In addition, the proposed method is orthogonal to existing methods and operates as a plug-in component compatible with different personalization techniques. Extensive experiments across diverse scenarios--including short-to-long text generation, and web function calling--validate the effectiveness and compatibility of our approach. Results show that our method significantly enhances personalization performance in fast-shifting environments while maintaining robustness across varying interaction modes and context lengths. Implementation is available at https://github.com/KounianhuaDu/Fints.

---

### MDAS-GNN: Multi-Dimensional Spatiotemporal GNN with Spatial Diffusion for Urban Traffic Risk Forecasting

Authors: Ziyuan Gao
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27197v1

Traffic accidents represent a critical public health challenge, claiming over 1.35 million lives annually worldwide. Traditional accident prediction models treat road segments independently, failing to capture complex spatial relationships and temporal dependencies in urban transportation networks. This study develops MDAS-GNN, a Multi-Dimensional Attention-based Spatial-diffusion Graph Neural Network integrating three core risk dimensions: traffic safety, infrastructure, and environmental risk. The framework employs feature-specific spatial diffusion mechanisms and multi-head temporal attention to capture dependencies across different time horizons. Evaluated on UK Department for Transport accident data across Central London, South Manchester, and SE Birmingham, MDASGNN achieves superior performance compared to established baseline methods. The model maintains consistently low prediction errors across short, medium, and long-term periods, with particular strength in long-term forecasting. Ablation studies confirm that integrated multi-dimensional features outperform singlefeature approaches, reducing prediction errors by up to 40%. This framework provides civil engineers and urban planners with advanced predictive capabilities for transportation infrastructure design, enabling data-driven decisions for road network optimization, infrastructure resource improvements, and strategic safety interventions in urban development projects.

---

### MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models

Authors: Zixin Chen, Hongzhan Lin, Kaixin Li, Ziyang Luo, Yayue Deng, Jing Ma
Published: 2025-10-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.27196v1

The proliferation of memes on social media necessitates the capabilities of multimodal Large Language Models (mLLMs) to effectively understand multimodal harmfulness. Existing evaluation approaches predominantly focus on mLLMs' detection accuracy for binary classification tasks, which often fail to reflect the in-depth interpretive nuance of harmfulness across diverse contexts. In this paper, we propose MemeArena, an agent-based arena-style evaluation framework that provides a context-aware and unbiased assessment for mLLMs' understanding of multimodal harmfulness. Specifically, MemeArena simulates diverse interpretive contexts to formulate evaluation tasks that elicit perspective-specific analyses from mLLMs. By integrating varied viewpoints and reaching consensus among evaluators, it enables fair and unbiased comparisons of mLLMs' abilities to interpret multimodal harmfulness. Extensive experiments demonstrate that our framework effectively reduces the evaluation biases of judge agents, with judgment results closely aligning with human preferences, offering valuable insights into reliable and comprehensive mLLM evaluations in multimodal harmfulness understanding. Our code and data are publicly available at https://github.com/Lbotirx/MemeArena.

---

### Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions

Authors: Caixin Kang, Yifei Huang, Liangyang Ouyang, Mingfang Zhang, Yoichi Sato
Published: 2025-10-31
Categories: cs.CV, cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2510.27195v2

As AI systems become increasingly integrated into human lives, endowing them with robust social intelligence has emerged as a critical frontier. A key aspect of this intelligence is discerning truth from deception, a ubiquitous element of human interaction that is conveyed through a complex interplay of verbal language and non-verbal visual cues. However, automatic deception detection in dynamic, multi-party conversations remains a significant challenge. The recent rise of powerful Multimodal Large Language Models (MLLMs), with their impressive abilities in visual and textual understanding, makes them natural candidates for this task. Consequently, their capabilities in this crucial domain are mostly unquantified. To address this gap, we introduce a new task, Multimodal Interactive Veracity Assessment (MIVA), and present a novel multimodal dataset derived from the social deduction game Werewolf. This dataset provides synchronized video, text, with verifiable ground-truth labels for every statement. We establish a comprehensive benchmark evaluating state-of-the-art MLLMs, revealing a significant performance gap: even powerful models like GPT-4o struggle to distinguish truth from falsehood reliably. Our analysis of failure modes indicates that these models fail to ground language in visual social cues effectively and may be overly conservative in their alignment, highlighting the urgent need for novel approaches to building more perceptive and trustworthy AI systems.

---

### From product to system network challenges in system of systems lifecycle management

Authors: Vahid Salehi, Josef Vilsmeier, Shirui Wang
Published: 2025-10-31
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2510.27194v1

Today, products are no longer isolated artifacts, but nodes in networked systems. This means that traditional, linearly conceived life cycle models are reaching their limits: Interoperability across disciplines, variant and configuration management, traceability, and governance across organizational boundaries are becoming key factors. This collective contribution classifies the state of the art and proposes a practical frame of reference for SoS lifecycle management, model-based systems engineering (MBSE) as the semantic backbone, product lifecycle management (PLM) as the governance and configuration level, CAD-CAE as model-derived domains, and digital thread and digital twin as continuous feedback. Based on current literature and industry experience, mobility, healthcare, and the public sector, we identify four principles: (1) referenced architecture and data models, (2) end-to-end configuration sovereignty instead of tool silos, (3) curated models with clear review gates, and (4) measurable value contributions along time, quality, cost, and sustainability. A three-step roadmap shows the transition from product- to network- centric development: piloting with reference architecture, scaling across variant and supply chain spaces, organizational anchoring (roles, training, compliance). The results are increased change robustness, shorter throughput times, improved reuse, and informed sustainability decisions. This article is aimed at decision-makers and practitioners who want to make complexity manageable and design SoS value streams to be scalable.

---

### Vectorized Online POMDP Planning

Authors: Marcus Hoerger, Muhammad Sudrajat, Hanna Kurniawati
Published: 2025-10-31
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.27191v5

Planning under partial observability is an essential capability of autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framework for planning under partial observability problems, capturing the stochastic effects of actions and the limited information available through noisy observations. POMDP solving could benefit tremendously from massive parallelization on today's hardware, but parallelizing POMDP solvers has been challenging. Most solvers rely on interleaving numerical optimization over actions with the estimation of their values, which creates dependencies and synchronization bottlenecks between parallel processes that can offset the benefits of parallelization. In this paper, we propose Vectorized Online POMDP Planner (VOPP), a novel parallel online solver that leverages a recent POMDP formulation which analytically solves part of the optimization component, leaving numerical computations to consist of only estimation of expectations. VOPP represents all data structures related to planning as a collection of tensors, and implements all planning steps as fully vectorized computations over this representation. The result is a massively parallel online solver with no dependencies or synchronization bottlenecks between concurrent processes. Experimental results indicate that VOPP is at least $20\times$ more efficient in computing near-optimal solutions compared to an existing state-of-the-art parallel online solver. Moreover, VOPP outperforms state-of-the-art sequential online solvers, while using a planning budget that is $1000\times$ smaller.

---

### Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications

Authors: Zixuan Hu, Yongxian Wei, Li Shen, Zhenyi Wang, Lei Li, Chun Yuan, Dacheng Tao
Published: 2025-10-31
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.27186v1

Model inversion, which aims to reconstruct the original training data from pre-trained discriminative models, is especially useful when the original training data is unavailable due to privacy, usage rights, or size constraints. However, existing dense inversion methods attempt to reconstruct the entire image area, making them extremely inefficient when inverting high-resolution images from large-scale Vision Transformers (ViTs). We further identify two underlying causes of this inefficiency: the redundant inversion of noisy backgrounds and the unintended inversion of spurious correlations--a phenomenon we term "hallucination" in model inversion. To address these limitations, we propose a novel sparse model inversion strategy, as a plug-and-play extension to speed up existing dense inversion methods with no need for modifying their original loss functions. Specifically, we selectively invert semantic foregrounds while stopping the inversion of noisy backgrounds and potential spurious correlations. Through both theoretical and empirical studies, we validate the efficacy of our approach in achieving significant inversion acceleration (up to 3.79 faster) while maintaining comparable or even enhanced downstream performance in data-free model quantization and data-free knowledge transfer. Code is available at https://github.com/Egg-Hu/SMI.

---

### Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+

Authors: Mason Shipton, York Hay Ng, Aditya Khan, Phuong Hanh Hoang, Xiang Lu, A. Seza Doğruöz, En-Shiun Annie Lee
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27183v3

The URIEL+ linguistic knowledge base supports multilingual research by encoding languages through geographic, genetic, and typological vectors. However, data sparsity (e.g. missing feature types, incomplete language entries, and limited genealogical coverage) remains prevalent. This limits the usefulness of URIEL+ in cross-lingual transfer, particularly for supporting low-resource languages. To address this sparsity, we extend URIEL+ by introducing script vectors to represent writing system properties for 7,488 languages, integrating Glottolog to add 18,710 additional languages, and expanding lineage imputation for 26,449 languages by propagating typological and script features across genealogies. These improvements reduce feature sparsity by 14% for script vectors, increase language coverage by up to 19,015 languages (1,007%), and boost imputation quality metrics by up to 35%. Our benchmark on cross-lingual transfer tasks (oriented around low-resource languages) shows occasionally divergent performance compared to URIEL+, with performance gains up to 6% in certain setups.

---

### SERFLOW: A Cross-Service Cost Optimization Framework for SLO-Aware Dynamic ML Inference

Authors: Zongshun Zhang, Ibrahim Matta
Published: 2025-10-31
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2510.27182v1

Dynamic offloading of Machine Learning (ML) model partitions across different resource orchestration services, such as Function-as-a-Service (FaaS) and Infrastructure-as-a-Service (IaaS), can balance processing and transmission delays while minimizing costs of adaptive inference applications. However, prior work often overlooks real-world factors, such as Virtual Machine (VM) cold starts, requests under long-tail service time distributions, etc. To tackle these limitations, we model each ML query (request) as traversing an acyclic sequence of stages, wherein each stage constitutes a contiguous block of sparse model parameters ending in an internal or final classifier where requests may exit. Since input-dependent exit rates vary, no single resource configuration suits all query distributions. IaaS-based VMs become underutilized when many requests exit early, yet rapidly scaling to handle request bursts reaching deep layers is impractical. SERFLOW addresses this challenge by leveraging FaaS-based serverless functions (containers) and using stage-specific resource provisioning that accounts for the fraction of requests exiting at each stage. By integrating this provisioning with adaptive load balancing across VMs and serverless functions based on request ingestion, SERFLOW reduces cloud costs by over $23\%$ while efficiently adapting to dynamic workloads.

---

### Dual-level Progressive Hardness-Aware Reweighting for Cross-View Geo-Localization

Authors: Guozheng Zheng, Jian Guan, Mingjie Xie, Xuanjia Zhao, Congyi Fan, Shiheng Zhang, Pengming Feng
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27181v3

Cross-view geo-localization (CVGL) between drone and satellite imagery remains challenging due to severe viewpoint gaps and the presence of hard negatives, which are visually similar but geographically mismatched samples. Existing mining or reweighting strategies often use static weighting, which is sensitive to distribution shifts and prone to overemphasizing difficult samples too early, leading to noisy gradients and unstable convergence. In this paper, we present a Dual-level Progressive Hardness-aware Reweighting (DPHR) strategy. At the sample level, a Ratio-based Difficulty-Aware (RDA) module evaluates relative difficulty and assigns fine-grained weights to negatives. At the batch level, a Progressive Adaptive Loss Weighting (PALW) mechanism exploits a training-progress signal to attenuate noisy gradients during early optimization and progressively enhance hard-negative mining as training matures. Experiments on the University-1652 and SUES-200 benchmarks demonstrate the effectiveness and robustness of the proposed DPHR, achieving consistent improvements over state-of-the-art methods.

---

### SilhouetteTell: Practical Video Identification Leveraging Blurred Recordings of Video Subtitles

Authors: Guanchong Huang, Song Fang
Published: 2025-10-31
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2510.27179v1

Video identification attacks pose a significant privacy threat that can reveal videos that victims watch, which may disclose their hobbies, religious beliefs, political leanings, sexual orientation, and health status. Also, video watching history can be used for user profiling or advertising and may result in cyberbullying, discrimination, or blackmail. Existing extensive video inference techniques usually depend on analyzing network traffic generated by streaming online videos. In this work, we observe that the content of a subtitle determines its silhouette displayed on the screen, and identifying each subtitle silhouette also derives the temporal difference between two consecutive subtitles. We then propose SilhouetteTell, a novel video identification attack that combines the spatial and time domain information into a spatiotemporal feature of subtitle silhouettes. SilhouetteTell explores the spatiotemporal correlation between recorded subtitle silhouettes of a video and its subtitle file. It can infer both online and offline videos. Comprehensive experiments on off-the-shelf smartphones confirm the high efficacy of SilhouetteTell for inferring video titles and clips under various settings, including from a distance of up to 40 meters.

---

### A Polynomial-time Algorithm for Online Sparse Linear Regression with Improved Regret Bound under Weaker Conditions

Authors: Junfan Li, Shizhong Liao, Zenglin Xu, Liqiang Nie
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27177v1

In this paper, we study the problem of online sparse linear regression (OSLR) where the algorithms are restricted to accessing only $k$ out of $d$ attributes per instance for prediction, which was proved to be NP-hard. Previous work gave polynomial-time algorithms assuming the data matrix satisfies the linear independence of features, the compatibility condition, or the restricted isometry property. We introduce a new polynomial-time algorithm, which significantly improves previous regret bounds (Ito et al., 2017) under the compatibility condition that is weaker than the other two assumptions. The improvements benefit from a tighter convergence rate of the $\ell_1$-norm error of our estimators. Our algorithm leverages the well-studied Dantzig Selector, but importantly with several novel techniques, including an algorithm-dependent sampling scheme for estimating the covariance matrix, an adaptive parameter tuning scheme, and a batching online Newton step with careful initializations. We also give novel and non-trivial analyses, including an induction method for analyzing the $\ell_1$-norm error, careful analyses on the covariance of non-independent random variables, and a decomposition on the regret. We further extend our algorithm to OSLR with additional observations where the algorithms can observe additional $k_0$ attributes after each prediction, and improve previous regret bounds (Kale et al., 2017; Ito et al., 2017).

---

### Glia: A Human-Inspired AI for Automated Systems Design and Optimization

Authors: Pouya Hamadanian, Pantea Karimi, Arash Nasr-Esfahany, Kimia Noorbakhsh, Joseph Chandler, Ali ParandehGheibi, Mohammad Alizadeh, Hari Balakrishnan
Published: 2025-10-31
Categories: cs.AI, cs.CL, cs.DC
arXiv: https://arxiv.org/abs/2510.27176v5

Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human experts? We present Glia, an AI architecture for networked systems design that uses large language models (LLMs) in a human-inspired multi-agent workflow. Each agent specializes in reasoning, experimentation, and analysis, collaborating through an evaluation framework that grounds abstract reasoning in empirical feedback. Unlike prior ML-for-systems methods that optimize black-box policies, Glia generates interpretable designs and exposes its reasoning. When applied to a distributed GPU cluster for LLM inference, it produces new algorithms for request routing, scheduling, and auto-scaling that perform at human-expert levels in significantly less time, while yielding novel insights into workload behavior. Our results suggest that combining reasoning LLMs with structured experimentation, an AI can produce creative and understandable designs for complex systems problems.

---

### FMint-SDE: A Multimodal Foundation Model for Accelerating Numerical Simulation of SDEs via Error Correction

Authors: Jiaxin Yuan, Haizhao Yang, Maria Cameron
Published: 2025-10-31
Categories: cs.CE, cs.AI, cs.LG, math.DS
arXiv: https://arxiv.org/abs/2510.27173v2

Fast and accurate simulation of dynamical systems is a fundamental challenge across scientific and engineering domains. Traditional numerical integrators often face a trade-off between accuracy and computational efficiency, while existing neural network-based approaches typically require training a separate model for each case. To overcome these limitations, we introduce a novel multi-modal foundation model for large-scale simulations of differential equations: FMint-SDE (Foundation Model based on Initialization for stochastic differential equations). Based on a decoder-only transformer with in-context learning, FMint-SDE leverages numerical and textual modalities to learn a universal error-correction scheme. It is trained using prompted sequences of coarse solutions generated by conventional solvers, enabling broad generalization across diverse systems. We evaluate our models on a suite of challenging SDE benchmarks spanning applications in molecular dynamics, mechanical systems, finance, and biology. Experimental results show that our approach achieves a superior accuracy-efficiency tradeoff compared to classical solvers, underscoring the potential of FMint-SDE as a general-purpose simulation tool for dynamical systems.

---

### Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Authors: Zixuan Hu, Li Shen, Zhenyi Wang, Yongxian Wei, Dacheng Tao
Published: 2025-10-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.27172v1

Harmful fine-tuning poses critical safety risks to fine-tuning-as-a-service for large language models. Existing defense strategies preemptively build robustness via attack simulation but suffer from fundamental limitations: (i) the infeasibility of extending attack simulations beyond bounded threat models due to the inherent difficulty of anticipating unknown attacks, and (ii) limited adaptability to varying attack settings, as simulation fails to capture their variability and complexity. To address these challenges, we propose Bayesian Data Scheduler (BDS), an adaptive tuning-stage defense strategy with no need for attack simulation. BDS formulates harmful fine-tuning defense as a Bayesian inference problem, learning the posterior distribution of each data point's safety attribute, conditioned on the fine-tuning and alignment datasets. The fine-tuning process is then constrained by weighting data with their safety attributes sampled from the posterior, thus mitigating the influence of harmful data. By leveraging the post hoc nature of Bayesian inference, the posterior is conditioned on the fine-tuning dataset, enabling BDS to tailor its defense to the specific dataset, thereby achieving adaptive defense. Furthermore, we introduce a neural scheduler based on amortized Bayesian learning, enabling efficient transfer to new data without retraining. Comprehensive results across diverse attack and defense settings demonstrate the state-of-the-art performance of our approach. Code is available at https://github.com/Egg-Hu/Bayesian-Data-Scheduler.

---

### H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models

Authors: Mingyu Sung, Il-Min Kim, Sangseok Yun, Jae-Mo Kang
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27171v1

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate inference, they often create a challenging trade-off between speed and fidelity, suffering from quality degradation and high computational overhead. To address these limitations, we introduce H2-Cache, a novel hierarchical caching mechanism designed for modern generative diffusion model architectures. Our method is founded on the key insight that the denoising process can be functionally separated into a structure-defining stage and a detail-refining stage. H2-cache leverages this by employing a dual-threshold system, using independent thresholds to selectively cache each stage. To ensure the efficiency of our dual-check approach, we introduce pooled feature summarization (PFS), a lightweight technique for robust and fast similarity estimation. Extensive experiments on the Flux architecture demonstrate that H2-cache achieves significant acceleration (up to 5.08x) while maintaining image quality nearly identical to the baseline, quantitatively and qualitatively outperforming existing caching methods. Our work presents a robust and practical solution that effectively resolves the speed-quality dilemma, significantly lowering the barrier for the real-world application of high-fidelity diffusion models. Source code is available at https://github.com/Bluear7878/H2-cache-A-Hierarchical-Dual-Stage-Cache.

---

### DANCER: Dance ANimation via Condition Enhancement and Rendering with diffusion model

Authors: Yucheng Xing, Jinxing Yin, Xiaodong Liu
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27169v1

Recently, diffusion models have shown their impressive ability in visual generation tasks. Besides static images, more and more research attentions have been drawn to the generation of realistic videos. The video generation not only has a higher requirement for the quality, but also brings a challenge in ensuring the video continuity. Among all the video generation tasks, human-involved contents, such as human dancing, are even more difficult to generate due to the high degrees of freedom associated with human motions. In this paper, we propose a novel framework, named as DANCER (Dance ANimation via Condition Enhancement and Rendering with Diffusion Model), for realistic single-person dance synthesis based on the most recent stable video diffusion model. As the video generation is generally guided by a reference image and a video sequence, we introduce two important modules into our framework to fully benefit from the two inputs. More specifically, we design an Appearance Enhancement Module (AEM) to focus more on the details of the reference image during the generation, and extend the motion guidance through a Pose Rendering Module (PRM) to capture pose conditions from extra domains. To further improve the generation capability of our model, we also collect a large amount of video data from Internet, and generate a novel datasetTikTok-3K to enhance the model training. The effectiveness of the proposed model has been evaluated through extensive experiments on real-world datasets, where the performance of our model is superior to that of the state-of-the-art methods. All the data and codes will be released upon acceptance.

---

### M^3Detection: Multi-Frame Multi-Level Feature Fusion for Multi-Modal 3D Object Detection with Camera and 4D Imaging Radar

Authors: Xiaozhi Li, Huijun Di, Jian Li, Feng Liu, Wei Liang
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27166v1

Recent advances in 4D imaging radar have enabled robust perception in adverse weather, while camera sensors provide dense semantic information. Fusing the these complementary modalities has great potential for cost-effective 3D perception. However, most existing camera-radar fusion methods are limited to single-frame inputs, capturing only a partial view of the scene. The incomplete scene information, compounded by image degradation and 4D radar sparsity, hinders overall detection performance. In contrast, multi-frame fusion offers richer spatiotemporal information but faces two challenges: achieving robust and effective object feature fusion across frames and modalities, and mitigating the computational cost of redundant feature extraction. Consequently, we propose M^3Detection, a unified multi-frame 3D object detection framework that performs multi-level feature fusion on multi-modal data from camera and 4D imaging radar. Our framework leverages intermediate features from the baseline detector and employs the tracker to produce reference trajectories, improving computational efficiency and providing richer information for second-stage. In the second stage, we design a global-level inter-object feature aggregation module guided by radar information to align global features across candidate proposals and a local-level inter-grid feature aggregation module that expands local features along the reference trajectories to enhance fine-grained object representation. The aggregated features are then processed by a trajectory-level multi-frame spatiotemporal reasoning module to encode cross-frame interactions and enhance temporal representation. Extensive experiments on the VoD and TJ4DRadSet datasets demonstrate that M^3Detection achieves state-of-the-art 3D detection performance, validating its effectiveness in multi-frame detection with camera-4D imaging radar fusion.

---

### Generating Accurate and Detailed Captions for High-Resolution Images

Authors: Hankyeol Lee, Gawon Seo, Kyounggyu Lee, Dogun Kim, Kyungwoo Song, Jiyoung Jung
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27164v1

Vision-language models (VLMs) often struggle to generate accurate and detailed captions for high-resolution images since they are typically pre-trained on low-resolution inputs (e.g., 224x224 or 336x336 pixels). Downscaling high-resolution images to these dimensions may result in the loss of visual details and the omission of important objects. To address this limitation, we propose a novel pipeline that integrates vision-language models, large language models (LLMs), and object detection systems to enhance caption quality. Our proposed pipeline refines captions through a novel, multi-stage process. Given a high-resolution image, an initial caption is first generated using a VLM, and key objects in the image are then identified by an LLM. The LLM predicts additional objects likely to co-occur with the identified key objects, and these predictions are verified by object detection systems. Newly detected objects not mentioned in the initial caption undergo focused, region-specific captioning to ensure they are incorporated. This process enriches caption detail while reducing hallucinations by removing references to undetected objects. We evaluate the enhanced captions using pairwise comparison and quantitative scoring from large multimodal models, along with a benchmark for hallucination detection. Experiments on a curated dataset of high-resolution images demonstrate that our pipeline produces more detailed and reliable image captions while effectively minimizing hallucinations.

---

### MARIA: A Framework for Marginal Risk Assessment without Ground Truth in AI Systems

Authors: Jieshan Chen, Suyu Ma, Qinghua Lu, Sung Une Lee, Liming Zhu
Published: 2025-10-31
Categories: cs.SE, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.27163v1

Before deploying an AI system to replace an existing process, it must be compared with the incumbent to ensure improvement without added risk. Traditional evaluation relies on ground truth for both systems, but this is often unavailable due to delayed or unknowable outcomes, high costs, or incomplete data, especially for long-standing systems deemed safe by convention. The more practical solution is not to compute absolute risk but the difference between systems. We therefore propose a marginal risk assessment framework, that avoids dependence on ground truth or absolute risk. It emphasizes three kinds of relative evaluation methodology, including predictability, capability and interaction dominance. By shifting focus from absolute to relative evaluation, our approach equips software teams with actionable guidance: identifying where AI enhances outcomes, where it introduces new risks, and how to adopt such systems responsibly.

---

### How Close Are We? Limitations and Progress of AI Models in Banff Lesion Scoring

Authors: Yanfan Zhu, Juming Xiong, Ruining Deng, Yu Wang, Yaohong Wang, Shilin Zhao, Mengmeng Yin, Yuqing Liu, Haichun Yang, Yuankai Huo
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27158v1

The Banff Classification provides the global standard for evaluating renal transplant biopsies, yet its semi-quantitative nature, complex criteria, and inter-observer variability present significant challenges for computational replication. In this study, we explore the feasibility of approximating Banff lesion scores using existing deep learning models through a modular, rule-based framework. We decompose each Banff indicator - such as glomerulitis (g), peritubular capillaritis (ptc), and intimal arteritis (v) - into its constituent structural and inflammatory components, and assess whether current segmentation and detection tools can support their computation. Model outputs are mapped to Banff scores using heuristic rules aligned with expert guidelines, and evaluated against expert-annotated ground truths. Our findings highlight both partial successes and critical failure modes, including structural omission, hallucination, and detection ambiguity. Even when final scores match expert annotations, inconsistencies in intermediate representations often undermine interpretability. These results reveal the limitations of current AI pipelines in replicating computational expert-level grading, and emphasize the importance of modular evaluation and computational Banff grading standard in guiding future model development for transplant pathology.

---

### Hierarchical Fusion of Local and Global Visual Features with Mixture-of-Experts for Remote Sensing Image Scene Classification

Authors: Yuanhao Tang, Xuechao Zou, Zhengpei Hu, Junliang Xing, Chengkun Zhang, Jianqiang Huang
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27155v2

Remote sensing image scene classification remains a challenging task, primarily due to the complex spatial structures and multi-scale characteristics of ground objects. Although CNN-based methods excel at extracting local inductive biases, and Mamba-based approaches demonstrate impressive capabilities in efficiently capturing global sequential context, relying on a single paradigm restricts the model's ability to simultaneously characterize fine-grained textures and complex spatial structures. To tackle this, we propose a parallel heterogeneous encoder, a hierarchical fusion module designed to achieve effective local-global co-representation. It consists of two parallel pathways: a local visual encoder for extracting multi-scale local visual features, and a global visual encoder for capturing efficient global visual features. The core innovation lies in its hierarchical fusion module, which progressively aggregates multi-scale features from both pathways, enabling dynamic cross-level feature interaction and contextual reconstruction to produce highly discriminative representations. These fused features are then adaptively routed through a mixture-of-experts classifier head, which dynamically dispatches them to the most suitable experts for fine-grained scene recognition. Experiments on AID, NWPU-RESISC45, and UC Merced show that our model achieves 93.72%, 95.54%, and 96.92% accuracy, surpassing SOTA methods with an optimal balance of performance and efficiency. Code is available at https://anonymous.4open.science/r/classification-41DF.

---

### Exploring Landscapes for Better Minima along Valleys

Authors: Tong Zhao, Jiacheng Li, Yuanchang Zhou, Guangming Tan, Weile Jia
Published: 2025-10-31
Categories: cs.LG, cs.AI, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2510.27153v1

Finding lower and better-generalizing minima is crucial for deep learning. However, most existing optimizers stop searching the parameter space once they reach a local minimum. Given the complex geometric properties of the loss landscape, it is difficult to guarantee that such a point is the lowest or provides the best generalization. To address this, we propose an adaptor "E" for gradient-based optimizers. The adapted optimizer tends to continue exploring along landscape valleys (areas with low and nearly identical losses) in order to search for potentially better local minima even after reaching a local minimum. This approach increases the likelihood of finding a lower and flatter local minimum, which is often associated with better generalization. We also provide a proof of convergence for the adapted optimizers in both convex and non-convex scenarios for completeness. Finally, we demonstrate their effectiveness in an important but notoriously difficult training scenario, large-batch training, where Lamb is the benchmark optimizer. Our testing results show that the adapted Lamb, ALTO, increases the test accuracy (generalization) of the current state-of-the-art optimizer by an average of 2.5% across a variety of large-batch training tasks. This work potentially opens a new research direction in the design of optimization algorithms.

---

### HiGS: Hierarchical Generative Scene Framework for Multi-Step Associative Semantic Spatial Composition

Authors: Jiacheng Hong, Kunzhen Wu, Mingrui Yu, Yichao Gu, Shengze Xue, Shuangjiu Xiao, Deli Dong
Published: 2025-10-31
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2510.27148v1

Three-dimensional scene generation holds significant potential in gaming, film, and virtual reality. However, most existing methods adopt a single-step generation process, making it difficult to balance scene complexity with minimal user input. Inspired by the human cognitive process in scene modeling, which progresses from global to local, focuses on key elements, and completes the scene through semantic association, we propose HiGS, a hierarchical generative framework for multi-step associative semantic spatial composition. HiGS enables users to iteratively expand scenes by selecting key semantic objects, offering fine-grained control over regions of interest while the model completes peripheral areas automatically. To support structured and coherent generation, we introduce the Progressive Hierarchical Spatial-Semantic Graph (PHiSSG), which dynamically organizes spatial relationships and semantic dependencies across the evolving scene structure. PHiSSG ensures spatial and geometric consistency throughout the generation process by maintaining a one-to-one mapping between graph nodes and generated objects and supporting recursive layout optimization. Experiments demonstrate that HiGS outperforms single-stage methods in layout plausibility, style consistency, and user preference, offering a controllable and extensible paradigm for efficient 3D scene construction.

---

### SERVIMON: AI-Driven Predictive Maintenance and Real-Time Monitoring for Astronomical Observatories

Authors: Emilio Mastriani, Alessandro Costa, Federico Incardona, Kevin Munari, Sebastiano Spinello
Published: 2025-10-31
Categories: astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2510.27146v1

Objective: ServiMon is designed to offer a scalable and intelligent pipeline for data collection and auditing to monitor distributed astronomical systems such as the ASTRI Mini-Array. The system enhances quality control, predictive maintenance, and real-time anomaly detection for telescope operations. Methods: ServiMon integrates cloud-native technologies-including Prometheus, Grafana, Cassandra, Kafka, and InfluxDB-for telemetry collection and processing. It employs machine learning algorithms, notably Isolation Forest, to detect anomalies in Cassandra performance metrics. Key indicators such as read/write latency, throughput, and memory usage are continuously monitored, stored as time-series data, and preprocessed for feature engineering. Anomalies detected by the model are logged in InfluxDB v2 and accessed via Flux for real-time monitoring and visualization. Results: AI-based anomaly detection increases system resilience by identifying performance degradation at an early stage, minimizing downtime, and optimizing telescope operations. Additionally, ServiMon supports astrostatistical analysis by correlating telemetry with observational data, thus enhancing scientific data quality. AI-generated alerts also improve real-time monitoring, enabling proactive system management. Conclusion: ServiMon's scalable framework proves effective for predictive maintenance and real-time monitoring of astronomical infrastructures. By leveraging cloud and edge computing, it is adaptable to future large-scale experiments, optimizing both performance and cost. The combination of machine learning and big data analytics makes ServiMon a robust and flexible solution for modern and next-generation observational astronomy.

---

### Relation-Aware Bayesian Optimization of DBMS Configurations Guided by Affinity Scores

Authors: Sein Kwon, Seulgi Baek, Hyunseo Yang, Youngwan Jo, Sanghyun Park
Published: 2025-10-31
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2510.27145v1

Database Management Systems (DBMSs) are fundamental for managing large-scale and heterogeneous data, and their performance is critically influenced by configuration parameters. Effective tuning of these parameters is essential for adapting to diverse workloads and maximizing throughput while minimizing latency. Recent research has focused on automated configuration optimization using machine learning; however, existing approaches still exhibit several key limitations. Most tuning frameworks disregard the dependencies among parameters, assuming that each operates independently. This simplification prevents optimizers from leveraging relational effects across parameters, limiting their capacity to capture performancesensitive interactions. Moreover, to reduce the complexity of the high-dimensional search space, prior work often selects only the top few parameters for optimization, overlooking others that contribute meaningfully to performance. Bayesian Optimization (BO), the most common method for automatic tuning, is also constrained by its reliance on surrogate models, which can lead to unstable predictions and inefficient exploration. To overcome these limitations, we propose RelTune, a novel framework that represents parameter dependencies as a Relational Graph and learns GNN-based latent embeddings that encode performancerelevant semantics. RelTune further introduces Hybrid-Score-Guided Bayesian Optimization (HBO), which combines surrogate predictions with an Affinity Score measuring proximity to previously high-performing configurations. Experimental results on multiple DBMSs and workloads demonstrate that RelTune achieves faster convergence and higher optimization efficiency than conventional BO-based methods, achieving state-of-the-art performance across all evaluated scenarios.

---

### Improving Cross-view Object Geo-localization: A Dual Attention Approach with Cross-view Interaction and Multi-Scale Spatial Features

Authors: Xingtao Ling Yingying Zhu
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27139v1

Cross-view object geo-localization has recently gained attention due to potential applications. Existing methods aim to capture spatial dependencies of query objects between different views through attention mechanisms to obtain spatial relationship feature maps, which are then used to predict object locations. Although promising, these approaches fail to effectively transfer information between views and do not further refine the spatial relationship feature maps. This results in the model erroneously focusing on irrelevant edge noise, thereby affecting localization performance. To address these limitations, we introduce a Cross-view and Cross-attention Module (CVCAM), which performs multiple iterations of interaction between the two views, enabling continuous exchange and learning of contextual information about the query object from both perspectives. This facilitates a deeper understanding of cross-view relationships while suppressing the edge noise unrelated to the query object. Furthermore, we integrate a Multi-head Spatial Attention Module (MHSAM), which employs convolutional kernels of various sizes to extract multi-scale spatial features from the feature maps containing implicit correspondences, further enhancing the feature representation of the query object. Additionally, given the scarcity of datasets for cross-view object geo-localization, we created a new dataset called G2D for the "Ground-to-Drone" localization task, enriching existing datasets and filling the gap in "Ground-to-Drone" localization task. Extensive experiments on the CVOGL and G2D datasets demonstrate that our proposed method achieves high localization accuracy, surpassing the current state-of-the-art.

---

### FairAD: Computationally Efficient Fair Graph Clustering via Algebraic Distance

Authors: Minh Phu Vuong, Young-Ju Lee, Iván Ojeda-Ruiz, Chul-Ho Lee
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27136v1

Due to the growing concern about unsavory behaviors of machine learning models toward certain demographic groups, the notion of 'fairness' has recently drawn much attention from the community, thereby motivating the study of fairness in graph clustering. Fair graph clustering aims to partition the set of nodes in a graph into $k$ disjoint clusters such that the proportion of each protected group within each cluster is consistent with the proportion of that group in the entire dataset. It is, however, computationally challenging to incorporate fairness constraints into existing graph clustering algorithms, particularly for large graphs. To address this problem, we propose FairAD, a computationally efficient fair graph clustering method. It first constructs a new affinity matrix based on the notion of algebraic distance such that fairness constraints are imposed. A graph coarsening process is then performed on this affinity matrix to find representative nodes that correspond to $k$ clusters. Finally, a constrained minimization problem is solved to obtain the solution of fair clustering. Experiment results on the modified stochastic block model and six public datasets show that FairAD can achieve fair clustering while being up to 40 times faster compared to state-of-the-art fair graph clustering algorithms.

---

### E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources

Authors: Tong Shen, Jingai Yu, Dong Zhou, Dong Li, Emad Barsoum
Published: 2025-10-31
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.27135v1

Diffusion models have shown strong capabilities in generating high-quality images from text prompts. However, these models often require large-scale training data and significant computational resources to train, or suffer from heavy structure with high latency. To this end, we propose Efficient Multimodal Diffusion Transformer (E-MMDiT), an efficient and lightweight multimodal diffusion model with only 304M parameters for fast image synthesis requiring low training resources. We provide an easily reproducible baseline with competitive results. Our model for 512px generation, trained with only 25M public data in 1.5 days on a single node of 8 AMD MI300X GPUs, achieves 0.66 on GenEval and easily reaches to 0.72 with some post-training techniques such as GRPO. Our design philosophy centers on token reduction as the computational cost scales significantly with the token count. We adopt a highly compressive visual tokenizer to produce a more compact representation and propose a novel multi-path compression module for further compression of tokens. To enhance our design, we introduce Position Reinforcement, which strengthens positional information to maintain spatial coherence, and Alternating Subregion Attention (ASA), which performs attention within subregions to further reduce computational cost. In addition, we propose AdaLN-affine, an efficient lightweight module for computing modulation parameters in transformer blocks. Our code is available at https://github.com/AMD-AGI/Nitro-E and we hope E-MMDiT serves as a strong and practical baseline for future research and contributes to democratization of generative AI models.

---

### WildfireX-SLAM: A Large-scale Low-altitude RGB-D Dataset for Wildfire SLAM and Beyond

Authors: Zhicong Sun, Jacqueline Lo, Jinxing Hu
Published: 2025-10-31
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2510.27133v1

3D Gaussian splatting (3DGS) and its subsequent variants have led to remarkable progress in simultaneous localization and mapping (SLAM). While most recent 3DGS-based SLAM works focus on small-scale indoor scenes, developing 3DGS-based SLAM methods for large-scale forest scenes holds great potential for many real-world applications, especially for wildfire emergency response and forest management. However, this line of research is impeded by the absence of a comprehensive and high-quality dataset, and collecting such a dataset over real-world scenes is costly and technically infeasible. To this end, we have built a large-scale, comprehensive, and high-quality synthetic dataset for SLAM in wildfire and forest environments. Leveraging the Unreal Engine 5 Electric Dreams Environment Sample Project, we developed a pipeline to easily collect aerial and ground views, including ground-truth camera poses and a range of additional data modalities from unmanned aerial vehicle. Our pipeline also provides flexible controls on environmental factors such as light, weather, and types and conditions of wildfire, supporting the need for various tasks covering forest mapping, wildfire emergency response, and beyond. The resulting pilot dataset, WildfireX-SLAM, contains 5.5k low-altitude RGB-D aerial images from a large-scale forest map with a total size of 16 km2. On top of WildfireX-SLAM, a thorough benchmark is also conducted, which not only reveals the unique challenges of 3DGS-based SLAM in the forest but also highlights potential improvements for future works. The dataset and code will be publicly available. Project page: https://zhicongsun.github.io/wildfirexslam.

---

### Exploring the Utilities of the Rationales from Large Language Models to Enhance Automated Essay Scoring

Authors: Hong Jiao, Hanna Choi, Haowei Hua
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27131v1

This study explored the utilities of rationales generated by GPT-4.1 and GPT-5 in automated scoring using Prompt 6 essays from the 2012 Kaggle ASAP data. Essay-based scoring was compared with rationale-based scoring. The study found in general essay-based scoring performed better than rationale-based scoring with higher Quadratic Weighted Kappa (QWK). However, rationale-based scoring led to higher scoring accuracy in terms of F1 scores for score 0 which had less representation due to class imbalance issues. The ensemble modeling of essay-based scoring models increased the scoring accuracy at both specific score levels and across all score levels. The ensemble modeling of essay-based scoring and each of the rationale-based scoring performed about the same. Further ensemble of essay-based scoring and both rationale-based scoring yielded the best scoring accuracy with QWK of 0.870 compared with 0.848 reported in literature.

---

### AI Agents in Drug Discovery

Authors: Srijit Seal, Dinh Long Huynh, Moudather Chelbi, Sara Khosravi, Ankur Kumar, Mattson Thieme, Isaac Wilks, Mark Davies, Jessica Mustali, Yannick Sun, Nick Edwards, Daniil Boiko et al.
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27130v1

Artificial intelligence (AI) agents are emerging as transformative tools in drug discovery, with the ability to autonomously reason, act, and learn through complicated research workflows. Building on large language models (LLMs) coupled with perception, computation, action, and memory tools, these agentic AI systems could integrate diverse biomedical data, execute tasks, carry out experiments via robotic platforms, and iteratively refine hypotheses in closed loops. We provide a conceptual and technical overview of agentic AI architectures, ranging from ReAct and Reflection to Supervisor and Swarm systems, and illustrate their applications across key stages of drug discovery, including literature synthesis, toxicity prediction, automated protocol generation, small-molecule synthesis, drug repurposing, and end-to-end decision-making. To our knowledge, this represents the first comprehensive work to present real-world implementations and quantifiable impacts of agentic AI systems deployed in operational drug discovery settings. Early implementations demonstrate substantial gains in speed, reproducibility, and scalability, compressing workflows that once took months into hours while maintaining scientific traceability. We discuss the current challenges related to data heterogeneity, system reliability, privacy, and benchmarking, and outline future directions towards technology in support of science and translation.

---

### ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding

Authors: Haonan Wang, Jingyu Lu, Hongrui Li, Xiaomeng Li
Published: 2025-10-31
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.27128v1

Recent advances in neural decoding have enabled the reconstruction of visual experiences from brain activity, positioning fMRI-to-image reconstruction as a promising bridge between neuroscience and computer vision. However, current methods predominantly rely on subject-specific models or require subject-specific fine-tuning, limiting their scalability and real-world applicability. In this work, we introduce ZEBRA, the first zero-shot brain visual decoding framework that eliminates the need for subject-specific adaptation. ZEBRA is built on the key insight that fMRI representations can be decomposed into subject-related and semantic-related components. By leveraging adversarial training, our method explicitly disentangles these components to isolate subject-invariant, semantic-specific representations. This disentanglement allows ZEBRA to generalize to unseen subjects without any additional fMRI data or retraining. Extensive experiments show that ZEBRA significantly outperforms zero-shot baselines and achieves performance comparable to fully finetuned models on several metrics. Our work represents a scalable and practical step toward universal neural decoding. Code and model weights are available at: https://github.com/xmed-lab/ZEBRA.

---

### AURA: A Reinforcement Learning Framework for AI-Driven Adaptive Conversational Surveys

Authors: Jinwen Tang, Yi Shang
Published: 2025-10-31
Categories: cs.HC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.27126v2

Conventional online surveys provide limited personalization, often resulting in low engagement and superficial responses. Although AI survey chatbots improve convenience, most are still reactive: they rely on fixed dialogue trees or static prompt templates and therefore cannot adapt within a session to fit individual users, which leads to generic follow-ups and weak response quality. We address these limitations with AURA (Adaptive Understanding through Reinforcement Learning for Assessment), a reinforcement learning framework for AI-driven adaptive conversational surveys. AURA quantifies response quality using a four-dimensional LSDE metric (Length, Self-disclosure, Emotion, and Specificity) and selects follow-up question types via an epsilon-greedy policy that updates the expected quality gain within each session. Initialized with priors extracted from 96 prior campus-climate conversations (467 total chatbot-user exchanges), the system balances exploration and exploitation across 10-15 dialogue exchanges, dynamically adapting to individual participants in real time. In controlled evaluations, AURA achieved a +0.076 mean gain in response quality and a statistically significant improvement over non-adaptive baselines (p=0.044, d=0.66), driven by a 63% reduction in specification prompts and a 10x increase in validation behavior. These results demonstrate that reinforcement learning can give survey chatbots improved adaptivity, transforming static questionnaires into interactive, self-improving assessment systems.

---

### Group-Sensitive Offline Contextual Bandits

Authors: Yihong Guo, Junjie Luo, Guodong Gao, Ritu Agarwal, Anqi Liu
Published: 2025-10-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.27123v2

Offline contextual bandits allow one to learn policies from historical/offline data without requiring online interaction. However, offline policy optimization that maximizes overall expected rewards can unintentionally amplify the reward disparities across groups. As a result, some groups might benefit more than others from the learned policy, raising concerns about fairness, especially when the resources are limited. In this paper, we study a group-sensitive fairness constraint in offline contextual bandits, reducing group-wise reward disparities that may arise during policy learning. We tackle the following common-parity requirements: the reward disparity is constrained within some user-defined threshold or the reward disparity should be minimized during policy optimization. We propose a constrained offline policy optimization framework by introducing group-wise reward disparity constraints into an off-policy gradient-based optimization procedure. To improve the estimation of the group-wise reward disparity during training, we employ a doubly robust estimator and further provide a convergence guarantee for policy optimization. Empirical results in synthetic and real-world datasets demonstrate that our method effectively reduces reward disparities while maintaining competitive overall performance.

---

### Probability Distributions Computed by Autoregressive Transformers

Authors: Andy Yang, Anej Svete, Jiaoda Li, Anthony Widjaja Lin, Jonathan Rawski, Ryan Cotterell, David Chiang
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27118v4

Most expressivity results for transformers treat them as language recognizers -- devices that accept or reject strings -- rather than as they are used in practice: as language models that generate strings autoregressively and probabilistically. We characterize the probability distributions that transformer language models can express. We show that making transformer language recognizers autoregressive can sometimes increase their expressivity, and that making them probabilistic can break equivalences that hold in the non-probabilistic case. Our overall contribution is to tease apart what functions transformers are capable of expressing in their most common use case as language models.

---

### Learning Robust Visuomotor Policies via Dynamics Alignment

Authors: Dohyeok Lee, Jung Min Lee, Munkyung Kim, Seokhun Ju, Jin Woo Koo, Kyungjae Lee, Dohyeong Kim, Taehyun Cho, Tapomayukh Bhattacharjee, Jungwoo Lee
Published: 2025-10-31
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2510.27114v2

Generative BC policies model expert action distributions well, but they do not explicitly reason about what scene a candidate action would produce, so they cannot tell whether it reaches a task-relevant state. We address this by coupling action generation with an action-conditioned dynamics model that predicts the future observations induced by actions. However, naively placing such a dynamics model inside a generative policy creates a circular dependency. Future observations are needed to guide action generation, yet those observations can only be predicted from the action samples being generated. We introduce Dynamics-Aligned Flow Matching Policy (DAP), where a flow matching policy and an action-conditioned flow matching dynamics model co-sample actions and future observations through flow extrapolation. At each step the two flows correct each other, and the samples converge to a self-consistent action and future pair on which the policy and dynamics model agree. Across four simulated tasks and three real-world tasks, DAP achieves the highest average success rate, with relative improvements of 56.5% in simulation and 33.3% in the real world over the strongest baseline in each setting. Moreover, when the future-observation estimate is corrupted at inference time, DAP recovers a self-consistent action-future pair through iterative refinement, whereas video-conditioned and post-hoc dynamics baselines, which use a fixed future surrogate, degrade or fail.

---

### Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks

Authors: Rajarshi Haldar, Julia Hockenmaier
Published: 2025-10-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.27106v1

As Natural Language Generation (NLG) continues to be widely adopted, properly assessing it has become quite difficult. Lately, using large language models (LLMs) for evaluating these generations has gained traction, as they tend to align more closely with human preferences than conventional n-gram or embedding-based metrics. In our experiments, we show that LLM judges have low intra-rater reliability in their assigned scores across different runs. This variance makes their ratings inconsistent, almost arbitrary in the worst case, making it difficult to measure how good their judgments actually are. We quantify this inconsistency across different NLG tasks and benchmarks and see if judicious use of LLM judges can still be useful following proper guidelines.

---

### Expressive Range Characterization of Open Text-to-Audio Models

Authors: Jonathan Morse, Azadeh Naderi, Swen Gaudl, Mark Cartwright, Amy K. Hoover, Mark J. Nelson
Published: 2025-10-31
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.27102v1

Text-to-audio models are a type of generative model that produces audio output in response to a given textual prompt. Although level generators and the properties of the functional content that they create (e.g., playability) dominate most discourse in procedurally generated content (PCG), games that emotionally resonate with players tend to weave together a range of creative and multimodal content (e.g., music, sounds, visuals, narrative tone), and multimodal models have begun seeing at least experimental use for this purpose. However, it remains unclear what exactly such models generate, and with what degree of variability and fidelity: audio is an extremely broad class of output for a generative system to target. Within the PCG community, expressive range analysis (ERA) has been used as a quantitative way to characterize generators' output space, especially for level generators. This paper adapts ERA to text-to-audio models, making the analysis tractable by looking at the expressive range of outputs for specific, fixed prompts. Experiments are conducted by prompting the models with several standardized prompts derived from the Environmental Sound Classification (ESC-50) dataset. The resulting audio is analyzed along key acoustic dimensions (e.g., pitch, loudness, and timbre). More broadly, this paper offers a framework for ERA-based exploratory evaluation of generative audio models.

---

### Hierarchical Bayesian Model for Gene Deconvolution and Functional Analysis in Human Endometrium Across the Menstrual Cycle

Authors: Crystal Su, Kuai Yu, Mingyuan Shao, Daniel Bauer
Published: 2025-10-31
Categories: cs.LG, q-bio.GN
arXiv: https://arxiv.org/abs/2510.27097v2

Bulk tissue RNA sequencing of heterogeneous samples provides averaged gene expression profiles, obscuring cell type-specific dynamics. To address this, we present a probabilistic hierarchical Bayesian model that deconvolves bulk RNA-seq data into constituent cell-type expression profiles and proportions, leveraging a high-resolution single-cell reference. We apply our model to human endometrial tissue across the menstrual cycle, a context characterized by dramatic hormone-driven cellular composition changes. Our extended framework provides a principled inference of cell type proportions and cell-specific gene expression changes across cycle phases. We demonstrate the model's structure, priors, and inference strategy in detail, and we validate its performance with simulations and comparisons to existing methods. The results reveal dynamic shifts in epithelial, stromal, and immune cell fractions between menstrual phases, and identify cell-type-specific differential gene expression associated with endometrial function (e.g., decidualization markers in stromal cells during the secretory phase). We further conduct robustness tests and show that our Bayesian approach is resilient to reference mismatches and noise. Finally, we discuss the biological significance of our findings, potential clinical implications for fertility and endometrial disorders, and future directions, including integration of spatial transcriptomics.

---

### CombiGraph-Vis: A Curated Multimodal Olympiad Benchmark for Discrete Mathematical Reasoning

Authors: Hamed Mahdavi, Pouria Mahdavinia, Alireza Farhadi, Pegah Mohammadipour, Samira Malek, Majid Daliri, Pedram Mohammadipour, Alireza Hashemi, Amir Khasahmadi, Vasant Honavar
Published: 2025-10-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.27094v1

State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 of 6 problems. Given this progress, we assess how well these models can grade proofs: detecting errors, judging their severity, and assigning fair scores beyond binary correctness. We study proof-analysis capabilities using a corpus of 90 Gemini 2.5 Pro-generated solutions that we grade on a 1-4 scale with detailed error annotations, and on MathArena solution sets for IMO/USAMO 2025 scored on a 0-7 scale. Our analysis shows that models can reliably flag incorrect (including subtly incorrect) solutions but exhibit calibration gaps in how partial credit is assigned. To address this, we introduce agentic workflows that extract and analyze reference solutions and automatically derive problem-specific rubrics for a multi-step grading process. We instantiate and compare different design choices for the grading workflows, and evaluate their trade-offs. Across our annotated corpus and MathArena, our proposed workflows achieve higher agreement with human grades and more consistent handling of partial credit across metrics. We release all code, data, and prompts/logs to facilitate future research.

---